Search in Publications

Found 5164 publications

Fuzzy flip-flop based neural network as a function approximator

László Gál Rita Lovassy L. T. Koczy

Publication Name: Cimsa 2008 IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings

Publication Date: 2008-09-26

Volume: Unknown

Issue: Unknown

Page Range: 44-49

Description:

Artificial neural networks and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A family of fuzzy flip-flops is proposed, based on an artificial neural network-like structure which is suitable for approximating many-input one-output nonlinear functions. The neurons in the multilayer perceptron networks typically employ sigmoidal activation functions. The next state of the fuzzy J-K flip-flops (F3) using Yager and Dombi operators present quasi-S-shaped characteristics. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such fuzzy units. Each of the two candidates for F 3-based neurons is examined for its training capability by evaluating and comparing the approximation properties in the context of different transcendental functions with one-input and multi-input cases. Simulation results are presented. ©2008 IEEE.

Open Access: Yes

DOI: 10.1109/CIMSA.2008.4595830

Experimental result on supersonic flow simulation on emulated digital CNN-UM

Sándor Kocsárdi Zoltán Nagy Árpád Csík P. Szolgay

Publication Name: Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

Publication Date: 2008-09-23

Volume: Unknown

Issue: Unknown

Page Range: 5

Description:

In the area of mechanical, aerospace, chemical and civil engineering the solution of partial differential equations (PDEs) has been one of the most important problems of mathematics for a long time. In this field, one of the most exciting areas is the simulation of fluid flow, which involves for example problems of air, sea and land vehicle motion. ©2008 IEEE.

Open Access: Yes

DOI: 10.1109/CNNA.2008.4588636

Two-dimensional compressible flow simulation on emulated digital CNN-UM

Sándor Kocsárdi Zoltán Nagy Árpád Csík P. Szolgay

Publication Name: Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

Publication Date: 2008-09-23

Volume: Unknown

Issue: Unknown

Page Range: 169-174

Description:

In the area of mechanical, aerospace, chemical and civil engineering the solution of partial differential equations (PDEs) has been one of the most important problems of mathematics for a long time. In this field, one of the most exciting areas is the simulation of fluid flow, which involves for example problems of air, sea and land vehicle motion. In this paper a CNNUM based solver of 2D inviscid, adiabatic, compressible fluids will be presented. The governing equations are solved by using firstand second-order numerical methods. Unfortunately the necessity of the coupled multi-layered computational structure with nonlinear, space-variant templates does not make it possible to utilize the huge computing power of the analog CNN-UM chips. To improve the performance of our solution emulated digital CNN-UM implemented on FPGA has been used. Properties of the implemented specialized architecture is examined in terms of area, speed and accuracy. ©2008 IEEE.

Open Access: Yes

DOI: 10.1109/CNNA.2008.4588672

An optimal quality management algorithm for road maintenance

Kornélia Ambrus-Somogyi Tamás Hartványi Habil A. Bako

Publication Name: 12th International Conference on Intelligent Engineering Systems Proceedings Ines 2008

Publication Date: 2008-09-02

Volume: Unknown

Issue: Unknown

Page Range: 233-236

Description:

The Road Management Systems (and the Pavement Management System-PMS) usually do not take into consideration the changes of future traffic. The maintenance and rehabilitation actions and the development of the road network structure as well as the changing traffic structure modify the amount of the traffic on the road sections. The deterioration process depends on mostly the volume of the traffic. That is why it is important to take into consideration the change of the traffic volume during the planning time horizon. In this paper some techniques are shown which are capable of handling this problem: in the multiperiod, long time model at each planning period the traffic volume change is take into consideration; in the ranking models the problem can also be handled and solved; in the case of the one-period Markov stable model to finding the solution is straightforward. In the multiperiod model a stepwise optimization procedure is used instead of the original algorithm. The objective function is also modified, so that the sum of the differences of the actual solution and the Markov stable model solution is minimized. The result of this algorithm provides a better quality of the road network. The amount of traffic on the sectors depends on the development of the road network also. © 2008 IEEE.

Open Access: Yes

DOI: 10.1109/INES.2008.4481300

Number archetypes in system realization theory concerning the fine structure constant

P. Várlaki László Nádai J. Bokor

Publication Name: 12th International Conference on Intelligent Engineering Systems Proceedings Ines 2008

Publication Date: 2008-09-02

Volume: Unknown

Issue: Unknown

Page Range: 83-92

Description:

In this paper we analyze in detail the central role of number '137', the so-called Fine Structure Constant in the collaboration of Pauli and Jung. First, we present the fascination or the obsession of Pauli for the interpretation of number '137'. Second, we treat the spontaneous messages originating from unconscious concerning number '137' in the well-known dreams of Pauli. We restrict our investigations to the dreams containing the especially important formulae of Fine Structure Constant (4π3 + π2 + π), and also that containing the so-called background models of mathematical control systems. Third, we shortly mention four of the numerous synchronicities arising during the Pauli-Jung collaboration. © 2008 IEEE.

Open Access: Yes

DOI: 10.1109/INES.2008.4481274

Fuzzy solution for non-linear quality models

J. Botzheim P. Földesi L. T. Koczy

Publication Name: 12th International Conference on Intelligent Engineering Systems Proceedings Ines 2008

Publication Date: 2008-09-01

Volume: Unknown

Issue: Unknown

Page Range: 269-275

Description:

For designing and developing products/services it is vital to know the relevancy of the performance generated by each technical attribute and how they can increase customer satisfaction. Improving the parameters of technical attributes requires financial resources, and the budgets are generally limited. Thus the optimum target is to achieve maximum customer satisfaction within given financial limits. Kano's quality model classifies the relationships between customer satisfaction and attribute-level performance and indicates that some of the attributes have a non-linear relationship to satisfaction, rather power-function should be used. For the customers' subjective evaluation these relationships are not deterministic and are uncertain. This paper proposes a method for fuzzy extension of Kano's model and presents numerical examples that can prove the efficiency of bacterial evolutionary algorithm in as well. © 2008 IEEE.

Open Access: Yes

DOI: 10.1109/INES.2008.4481306

Fuzzy signature based mobil robot motion control system

Á Ballagi L. T. Koczy

Publication Name: Sami 2008 6th International Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2008-08-25

Volume: Unknown

Issue: Unknown

Page Range: 29-33

Description:

The differentially steered drive system used in many robots is essentially the same arrangement as that used in a wheelchair. Thus, steering the robot is just a matter of varying the speeds of the drive wheels. At least two independent driving chain are used in most of differentially steered drive system. Each driver wheel has the own controller in a traditional motion system, which give a hard tuned, rigid arrangement. In this paper we propose a complex lateral drift control method base on fuzzy signatures. This method inspects the motion system as a whole, unlike as simple parts of a complex system. The state space is written down by fuzzy signatures which adds up flexibility, adaptability and learning ability to system. © 2008 IEEE.

Open Access: Yes

DOI: 10.1109/SAMI.2008.4469193

Fuzzy rule base extraction by the improved bacterial memetic algorithm

J. Botzheim László Gál A. E. Ruano L. T. Koczy

Publication Name: Sami 2008 6th International Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2008-08-25

Volume: Unknown

Issue: Unknown

Page Range: 49-53

Description:

In this paper we introduce new methods for handling knot order violation occurred in the Bacterial Memetic Algorithm (BMA) used for fuzzy rule base extraction. These methods perform slightly better than the method used before and are easier to integrate with the Bacterial Memetic Algorithm. ©2008 IEEE.

Open Access: Yes

DOI: 10.1109/SAMI.2008.4469132

Selection from a fuzzy signature database by Mamdani-algorithm

Katalin Tamás L. T. Koczy

Publication Name: Sami 2008 6th International Symposium on Applied Machine Intelligence and Informatics Proceedings

Publication Date: 2008-08-25

Volume: Unknown

Issue: Unknown

Page Range: 63-68

Description:

There are many complex, well structured problems, where a hierarchical structure within the data is present. This means, that one or several components of the structure are determined at a higher level by a sub-tree of other components. The concept of fuzzy signatures was introduced to help model these kinds of problems. The data set belonging to a problem has an arbitrary structure, but due to some missing components, the structures of the data may slightly differ. So that these data can be evaluated, aggregation operators are given for each node in the arbitrary structure for the purpose of modifying the structure. To deduce a conclusion for an observation from a data set having the structure mentioned above, fuzzy signature based rule bases and the generalisation of Mamdani-type inference were introduced. In this paper the formerly introduced idea of Mamdani-type inference in fuzzy signature based rule bases will be used for selecting records from an available data base which maximally match the requirements specified in a pattern. Finally a possible application on a realistic example with missing data components will be shown. © 2008 IEEE.

Open Access: Yes

DOI: 10.1109/SAMI.2008.4469135